Data Agents: Levels, State of the Art, and Open Problems

TL;DR

This paper introduces a hierarchical taxonomy of data agents from no autonomy to full autonomy, reviews current systems, and discusses future research challenges for autonomous data management and analysis.

Contribution

It proposes the first comprehensive taxonomy of data agents, clarifies capability boundaries, and provides a research roadmap for advancing autonomous data systems.

Findings

Present the L0-L5 taxonomy of data agents.

Review current L0-L2 data management systems.

Identify challenges for L4 and L5 autonomous data agents.

Abstract

Data agents are an emerging paradigm that leverages large language models (LLMs) and tool-using agents to automate data management, preparation, and analysis tasks. However, the term "data agent" is currently used inconsistently, conflating simple query responsive assistants with aspirational fully autonomous "data scientists". This ambiguity blurs capability boundaries and accountability, making it difficult for users, system builders, and regulators to reason about what a "data agent" can and cannot do. In this tutorial, we propose the first hierarchical taxonomy of data agents from Level 0 (L0, no autonomy) to Level 5 (L5, full autonomy). Building on this taxonomy, we will introduce a lifecycleand level-driven view of data agents. We will (1) present the L0-L5 taxonomy and the key evolutionary leaps that separate simple assistants from truly autonomous data agents, (2) review representative L0-L2 systems across data management, preparation, and analysis, (3) highlight emerging Proto-L3 systems that strive to autonomously orchestrate end-to-end data workflows to tackle diverse and comprehensive data-related tasks under supervision, and (4) discuss forward-looking research challenges towards proactive (L4) and generative (L5) data agents. We aim to offer both a practical map of today's systems and a research roadmap for the next decade of data-agent development.